© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128273
    Prev
    Next
    INDEX
    Explanations

    basic overview

    np_acts-logits-general · gemini-2.5-flash-lite

    geography and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ra
    0.53
    다
    0.51
    را
    0.47
    GEST
    0.46
    観
    0.46
    waard
    0.45
    reg
    0.45
    met
    0.45
     별
    0.44
    鵑
    0.44
    POSITIVE LOGITS
    ковая
    0.46
    ртка
    0.44
     jeszcze
    0.43
    ﻒ
    0.41
     até
    0.40
    ковые
    0.40
    GetWidth
    0.40
    او
    0.40
    देशीर
    0.39
    др
    0.39
    Activations Density 0.001%

    No Known Activations